Search Results (508)

Oblique photogrammetry-based 3D modeling is widely used for large-scale urban reconstruction. However, textures generated with photogrammetric techniques often exhibit scattered and irregular characteristics, which lead to significant challenges with texture seams and UV map discontinuities, increasing storage requirements and affecting rendering quality. In this paper, we propose a planar feature-preserving texture defragmentation method designed specifically for urban building models. Our approach leverages the multi-planar topology of buildings to optimize texture merging and reduce fragmentation. The proposed approach is composed of three main stages: the extraction of planar features from texture fragments; the employment of these planar elements as guiding constraints for merging adjacent texture fragments within a two-dimensional texture space; and an enhanced texture-packing algorithm designed for more regular texture charts to systematically generate refined texture atlas. Experiments on various urban building models demonstrate that our method significantly improves texture continuity and storage efficiency compared to traditional approaches, with both quantitative and qualitative validation. Full article

Given the recent proliferation of Unmanned Aerial Systems (UASs) and the consequent importance of counter-UASs, this project aims to perform the detection and tracking of small non-cooperative UASs using Electro-optical (EO) and Infrared (IR) sensors. Two data integration techniques, at the decision and pixel levels, are compared with the use of each sensor independently to evaluate the system robustness in different operational conditions. The data are submitted to a YOLOv7 detector merged with a ByteTrack tracker. For training and validation, additional efforts are made towards creating datasets of spatially and temporally aligned EO and IR annotated Unmanned Aerial Vehicle (UAV) frames and videos. These consist of the acquisition of real data captured from a workstation on the ground, followed by image calibration, image alignment, the application of bias-removal techniques, and data augmentation methods to artificially create images. The performance of the detector across datasets shows an average precision of 88.4%, recall of 85.4%, and [email protected] of 88.5%. Tests conducted on the decision-level fusion architecture demonstrate notable gains in recall and precision, although at the expense of lower frame rates. Precision, recall, and frame rate are not improved by the pixel-level fusion design. Full article

Change detection (CD) identifies surface changes by analyzing bi-temporal remote sensing (RS) images of the same region and is essential for effective urban planning, ensuring the optimal allocation of resources, and supporting disaster management efforts. However, deep-learning-based CD methods struggle with background noise and pseudo-changes due to local receptive field limitations or computing resource constraints, which limits long-range dependency capture and feature integration, normally resulting in fragmented detections and high false positive rates. To address these challenges, we propose a tree topology Mamba-guided network (TTMGNet) based on Mamba architecture, which combines the Mamba architecture for effectively capturing global features, a unique tree topology structure for retaining fine local details, and a hierarchical feature fusion mechanism that enhances multi-scale feature integration and robustness against noise. Specifically, the a Tree Topology Mamba Feature Extractor (TTMFE) leverages the similarity of pixels to generate minimum spanning tree (MST) topology sequences, guiding information aggregation and transmission. This approach utilizes a Tree Topology State Space Model (TTSSM) to embed spatial and positional information while preserving the global feature extraction capability, thereby retaining local features. Subsequently, the Hierarchical Incremental Aggregation Module is utilized to gradually align and merge features from deep to shallow layers to facilitate hierarchical feature integration. Through residual connections and cross-channel attention (CCA), HIAM enhances the interaction between neighboring feature maps, ensuring that critical features are retained and effectively utilized during the fusion process, thereby enabling more accurate detection results in CD. The proposed TTMGNet achieved F1 scores of 92.31% on LEVIR-CD, 90.94% on WHU-CD, and 77.25% on CL-CD, outperforming current mainstream methods in suppressing the impact of background noise and pseudo-change and more accurately identifying change regions. Full article

The advancement of geological big data has rendered data-driven methodologies increasingly vital in Mineral Prospectivity Mapping. The effective integration of quantitative and qualitative data, including experiential and knowledge-based insights, is crucial in geological data fusion. Specifically, the conversion of raw data into samples and the selection of predictive methods are two core issues that constitute the focus of this study. Traditional clustering methods require the user to specify the number of clusters in advance. The two-step clustering can automatically determine the clustering result ‘k’ while analyzing both continuous and categorical variables, by building a Cluster Feature (CF) and using information criteria to merge nodes. In this study, we conducted an analysis utilizing stream sediment element data, residual gravity anomalies, and fault distribution through the two-step clustering method. Factor analysis (FA) was employed to reduce 16 elemental variables from stream sediments into five uncorrelated continuous variables; additionally, residual gravity anomalies were transformed from continuous to categorical variables via an interval-based method before being combined with fault distribution, resulting in seven variables for clustering. The research findings indicate that categorical variables significantly influence clustering results; concurrently, as the importance of continuous variables within the cluster increases, so does k. When only one categorical variable is present, residual gravity anomalies show significantly better clustering than fault distribution; however, when two categorical variables are involved, it is essential to consider the quantity of categories: more categories lead to poorer quality. The results from the Jiaolai Basin’s northeastern margin indicate a significant correlation with known gold deposits; two-step clustering is a promising and effective method for improving mineral prospecting efforts. Full article

In complex environments, strawberry disease segmentation models face challenges, such as segmentation difficulties, excessive parameters, and high computational loads, making it difficult for these models to run effectively on devices with limited computational resources. To address the need for efficient running on low-power devices while ensuring effective disease segmentation in complex scenarios, this paper proposes BHI-YOLO, a lightweight instance segmentation model based on YOLOv8n-seg. First, the Universal Inverted Bottleneck (UIB) module is integrated into the backbone network and merged with the C2f module to create the C2f_UIB module; this approach reduces the parameter count while expanding the receptive field. Second, the HS-FPN is introduced to further reduce the parameter count and enhance the model’s ability to fuse features across different levels. Finally, by integrating the Inverted Residual Mobile Block (iRMB) with EMA to design the iRMA, the model is capable of efficiently combining global information to enhance local information. The experimental results demonstrate that the enhanced instance segmentation model for strawberry diseases achieved a mean average precision (mAP@50) of 93%. Compared to YOLOv8, which saw a 2.3% increase in mask mAP, the improved model reduced parameters by 47%, GFLOPs by 20%, and model size by 44.1%, achieving a relatively excellent lightweight effect. This study combines lightweight architecture with enhanced feature fusion, making the model more suitable for deployment on mobile devices, and provides a reference guide for strawberry disease segmentation applications in agricultural environments. Full article

SegContrast first paved the way for contrastive learning on outdoor point clouds. Its original formulation targeted individual scans in applications like autonomous driving and object detection. However, mobile mapping purposes such as digital twin cities and urban planning require large-scale dense datasets to capture the full complexity and diversity present in outdoor environments. In this paper, the SegContrast method is revisited and adapted to overcome its limitations associated with mobile mapping datasets, namely the scarcity of contrastive pairs and memory constraints. To overcome the scarcity of contrastive pairs, we propose the merging of heterogeneous datasets. However, this merging is not a straightforward procedure due to the variety of size and number of points in the point clouds of these datasets. Therefore, a data augmentation approach is designed to create a vast number of segments while optimizing the size of the point cloud samples to the allocated memory. This methodology, called CLOUDSPAM, guarantees the performance of the self-supervised model for both small- and large-scale mobile mapping point clouds. Overall, the results demonstrate the benefits of utilizing datasets with a wide range of densities and class diversity. CLOUDSPAM matched the state of the art on the KITTI-360 dataset, with a 63.6% mIoU, and came in second place on the Toronto-3D dataset. Finally, CLOUDSPAM achieved competitive results against its fully supervised counterpart with only 10% of labeled data. Full article

We introduce the concept-driven quantum neural network (CD-QNN), an innovative architecture designed to enhance the interpretability of quantum neural networks (QNNs). CD-QNN merges the representational capabilities of QNNs with the transparency of self-explanatory models by mapping input data into a human-understandable concept space and making decisions based on these concepts. The algorithmic design of CD-QNN is comprehensively analyzed, detailing the roles of the concept generator, feature extractor, and feature integrator in improving and balancing model expressivity and interpretability. Experimental results demonstrate that CD-QNN maintains high predictive accuracy while offering clear and meaningful explanations of its decision-making process. This paradigm shift in QNN design underscores the growing importance of interpretability in quantum artificial intelligence, positioning CD-QNN and its derivative technologies as pivotal in advancing reliable and interpretable quantum intelligent systems for future research and applications. Full article

Unmanaged forest ecosystems play a critical role in addressing the ongoing climate and biodiversity crises. As there is no commercial interest in monitoring the health and development of such inaccessible habitats, low-cost assessment approaches are needed. We used a method combining RGB imagery acquired using an Unmanned Aerial Vehicle (UAV), Sentinel-2 data, and field surveys to determine the carbon stock of an unmanaged forest in the UNESCO World Heritage Site wilderness area Dürrenstein-Lassingtal in Austria. The entry-level consumer drone (DJI Mavic Mini) and freely available Sentinel-2 multispectral datasets were used for the evaluation. We merged the Sentinel-2 derived vegetation index NDVI with aerial photogrammetry data and used an orthomosaic and a Digital Surface Model (DSM) to map the extent of woodland in the study area. The Random Forest (RF) machine learning (ML) algorithm was used to classify land cover. Based on the acquired field data, the average carbon stock per hectare of forest was determined to be 371.423 ± 51.106 t of CO₂ and applied to the ML-generated class Forest. An overall accuracy of 80.8% with a Cohen’s kappa value of 0.74 was achieved for the land cover classification, while the carbon stock of the living above-ground biomass (AGB) was estimated with an accuracy within 5.9% of field measurements. The proposed approach demonstrated that the combination of low-cost remote sensing data and field work can predict above-ground biomass with high accuracy. The results and the estimation error distribution highlight the importance of accurate field data. Full article

Substantial advancements have been achieved in hyperspectral image (HSI) classification through contemporary deep learning techniques. Nevertheless, the incorporation of an excessive number of irrelevant tokens in large-scale remote sensing data results in inefficient long-range modeling. To overcome this hurdle, this study introduces the Group-Sensitive Selective Perception Transformer (GSAT) framework, which builds upon the Vision Transformer (ViT) to enhance HSI classification outcomes. The innovation of the GSAT architecture is primarily evident in several key aspects. Firstly, the GSAT incorporates a Group-Sensitive Pixel Group Mapping (PGM) module, which organizes pixels into distinct groups. This allows the global self-attention mechanism to function within these groupings, effectively capturing local interdependencies within spectral channels. This grouping tactic not only boosts the model’s spatial awareness but also lessens computational complexity, enhancing overall efficiency. Secondly, the GSAT addresses the detrimental effects of superfluous tokens on model efficacy by introducing the Sensitivity Selection Framework (SSF) module. This module selectively identifies the most pertinent tokens for classification purposes, thereby minimizing distractions from extraneous information and bolstering the model’s representational strength. Furthermore, the SSF refines local representation through multi-scale feature selection, enabling the model to more effectively encapsulate feature data across various scales. Additionally, the GSAT architecture adeptly represents both global and local features of HSI data by merging global self-attention with local feature extraction. This integration strategy not only elevates classification precision but also enhances the model’s versatility in navigating complex scenes, particularly in urban mapping scenarios where it significantly outclasses previous deep learning methods. The advent of the GSAT architecture not only rectifies the inefficiencies of traditional deep learning approaches in processing extensive remote sensing imagery but also markededly enhances the performance of HSI classification tasks through the deployment of group-sensitive and selective perception mechanisms. It presents a novel viewpoint within the domain of hyperspectral image classification and is poised to propel further advancements in the field. Empirical testing on six standard HSI datasets confirms the superior performance of the proposed GSAT method in HSI classification, especially within urban mapping contexts, where it exceeds the capabilities of prior deep learning techniques. In essence, the GSAT architecture markedly refines HSI classification by pioneering group-sensitive pixel group mapping and selective perception mechanisms, heralding a significant breakthrough in hyperspectral image processing. Full article

Blueberries, as one of the more economically rewarding fruits in the fruit industry, play a significant role in fruit detection during their growing season, which is crucial for orchard farmers’ later harvesting and yield prediction. Due to the small size and dense growth of blueberry fruits, manual detection is both time-consuming and labor-intensive. We found that there are few studies utilizing drones for blueberry fruit detection. By employing UAV remote sensing technology and deep learning techniques for detection, substantial human, material, and financial resources can be saved. Therefore, this study collected and constructed a UAV remote sensing target detection dataset for blueberry canopy fruits in a real blueberry orchard environment, which can be used for research on remote sensing target detection of blueberries. To improve the detection accuracy of blueberry fruits, we proposed the PAC3 module, which incorporates location information encoding during the feature extraction process, allowing it to focus on the location information of the targets and thereby reducing the chances of missing blueberry fruits. We adopted a fast convolutional structure instead of the traditional convolutional structure, reducing the model’s parameter count and computational complexity. We proposed the PF-YOLO model and conducted experimental comparisons with several excellent models, achieving improvements in mAP of 5.5%, 6.8%, 2.5%, 2.1%, 5.7%, 2.9%, 1.5%, and 3.4% compared to Yolov5s, Yolov5l, Yolov5s-p6, Yolov5l-p6, Tph-Yolov5, Yolov8n, Yolov8s, and Yolov9c, respectively. We also introduced a non-maximal suppression algorithm, Cluster-NMF, which accelerates inference speed through matrix parallel computation and merges multiple high-quality target detection frames to generate an optimal detection frame, enhancing the efficiency of blueberry canopy fruit detection without compromising inference speed. Full article

China’s forests act as a large carbon sink and play a vital role in achieving the carbon neutrality goal by the 2060s. To achieve this goal, the magnitude and spatial patterns of forest carbon sinks must be accurately quantified. In this study, we aim to provide the longest estimate of forest biomass carbon storage and sinks in China at a 1 km spatial resolution from 1990 to 2021 by merging long-term observations from optical and microwave remote sensing datasets with a field-validated benchmark map. We explored the spatial characteristics of aboveground biomass (AGB) and belowground biomass (BGB) carbon in China’s forests, as well as variations in AGB carbon sinks. The average AGB and BGB carbon storage from 1990 to 2021 in China’s forests were 8.42 ± 0.96 Pg C and 1.9 ± 0.21 Pg C, respectively. The average annual AGB carbon sink during this period was approximately 0.083 ± 0.023 Pg C yr⁻¹. Forests in the southwest region contributed 31.15% of the forest AGB carbon sink in China and contributed 41.01% of the forest AGB carbon storage. Our study presents an effective tool for assessing changes in forest biomass carbon by leveraging comprehensive multi-source remote sensing data and highlights the importance of obtaining large-scale, high-quality, consistent, and accessible plot survey data to validate the earth observation of biomass. Full article

Accurate coffee plant counting is a crucial metric for yield estimation and a key component of precision agriculture. While multispectral UAV technology provides more accurate crop growth data, the varying spectral characteristics of coffee plants across different phenological stages complicate automatic plant counting. This study compared the performance of mainstream YOLO models for coffee detection and segmentation, identifying YOLOv9 as the best-performing model, with it achieving high precision in both detection (P = 89.3%, mAP50 = 94.6%) and segmentation performance (P = 88.9%, mAP50 = 94.8%). Furthermore, we studied various spectral combinations from UAV data and found that RGB was most effective during the flowering stage, while RGN (Red, Green, Near-infrared) was more suitable for non-flowering periods. Based on these findings, we proposed an innovative dual-channel non-maximum suppression method (dual-channel NMS), which merges YOLOv9 detection results from both RGB and RGN data, leveraging the strengths of each spectral combination to enhance detection accuracy and achieving a final counting accuracy of 98.4%. This study highlights the importance of integrating UAV multispectral technology with deep learning for coffee detection and offers new insights for the implementation of precision agriculture. Full article

(1) Background: Analyses of retrieved inserts allow for a better understanding of TKA failure mechanisms and the detection of factors that cause increased wear. The purpose of this implant retrieval study was to identify whether insert volumetric wear significantly differs among groups of common causes of total knee arthroplasty failure, whether there is a characteristic wear distribution pattern for a common cause of failure, and whether nominal insert size and component size ratio (femur-to-insert) influence linear and volumetric wear rates. (2) Methods: We digitally reconstructed 59 retrieved single-model cruciate-retaining inserts and computed their articular load-bearing surface wear utilizing an optical scanner and computer-aided design models as references. After comprehensively reviewing all cases, each was categorized into one or more of the following groups: prosthetic joint infection, osteolysis, clinical loosening of the component, joint malalignment or component malposition, instability, and other isolated causes. The associations between volumetric wear and causes of failure were estimated using a multiple linear regression model adjusted for time in situ. Insert linear penetration wear maps from the respective groups of failure were further processed and merged to create a single average binary image, highlighting a potential wear distribution pattern. The differences in wear rates according to nominal insert size (small vs. medium vs. large) and component size ratio (≤1 vs. >1) were tested using the Kruskal–Wallis test and the Mann–Whitney test, respectively. (3) Results: Patients with identified osteolysis alone and those also with clinical loosening of the component had significantly higher volumetric wear when compared to those without both causes (p = 0.016 and p = 0.009, respectively). All other causes were not significantly associated with volumetric wear. The instability group differentiated from the others with a combined peripheral antero-posterior wear distribution. Linear and volumetric wear rates showed no significant differences when compared by nominal insert size (small vs. medium vs. large, p = 0.563 and p = 0.747, respectively) or by component (femoral-to-insert) size ratio (≤1 vs. >1, p = 0.885 and p = 0.055, respectively). (4) Conclusions: The study found increased volumetric wear in cases of osteolysis alone, with greater wear when combined with clinical loosening compared to other groups. The instability group demonstrated a characteristic peripheral anterior and posterior wear pattern. Insert size and component size ratio seem not to influence wear rates. Full article

In response to the COVID-19 pandemic, governments worldwide have implemented mandatory face mask regulations in crowded public spaces, making the development of automatic face mask detection systems critical. To achieve robust face mask detection performance, a high-quality and comprehensive face mask dataset is required. However, due to the difficulty in obtaining face samples with masks in the real-world, public face mask datasets are often imbalanced, leading to the data imbalance problem in model training and negatively impacting detection performance. To address this problem, this paper proposes a novel recursive model-training technique designed to improve detection accuracy on imbalanced datasets. The proposed method recursively splits and merges the dataset based on the attribute characteristics of different classes, enabling more balanced and effective model training. Our approach demonstrates that the carefully designed splitting and merging of datasets can significantly enhance model-training performance. This method was evaluated using two imbalanced datasets. The experimental results show that the proposed recursive learning technique achieves a percentage increase (PI) of 84.5% in mean average precision ([email protected]) on the Kaggle dataset and of 186.3% on the Eden dataset compared to traditional supervised learning. Additionally, when combined with existing oversampling techniques, the PI on the Kaggle dataset further increases to 88.9%, highlighting the potential of the proposed method for improving detection accuracy in highly imbalanced datasets. Full article

Accurate detection and classification of traffic signs play a vital role in ensuring driver safety and supporting advancements in autonomous driving technology. This paper introduces a novel approach for traffic sign detection and recognition by integrating the Faster RCNN and YOLOX-Tiny models using a stacking ensemble technique. The innovative ensemble methodology creatively merges the strengths of both models, surpassing the limitations of individual algorithms and achieving superior performance in challenging real-world scenarios. The proposed model was evaluated on the CCTSDB dataset and the MTSD dataset, demonstrating competitive performance compared to traditional algorithms. All experiments were conducted using Python 3.8 on the same system equipped with an NVIDIA GTX 3060 12G graphics card. Our results show improved accuracy and efficiency in recognizing traffic signs in various real-world scenarios, including distant, close, complex, moderate, and simple settings, achieving a 4.78% increase in mean Average Precision (mAP) compared to Faster RCNN and improving Frames Per Second (FPS) by 8.1% and mAP by 6.18% compared to YOLOX-Tiny. Moreover, the proposed model exhibited notable precision in challenging scenarios such as ultra-long-distance detections, shadow occlusions, motion blur, and complex environments with diverse sign categories. These findings not only showcase the model’s robustness but also serve as a cornerstone in propelling the evolution of autonomous driving technology and sustainable development of future transportation. The results presented in this paper could potentially be integrated into advanced driver-assistance systems and autonomous vehicles, offering a significant step forward in enhancing road safety and traffic management. Full article